人工神经网络-近红外光谱法非破坏监测芦丁药品的质量

NONDESTRUCTIVE QUALITY CONTROL OF RUTIN PHARMACEUTICALS BY NEAR INFRARED REFLECTANCE SPECTROSCOPY AND ARTIFICIAL NEURAL NETWORK

用近红外漫反射光谱法非破坏监测芦丁药品的质量。利用人工神经网络化学计量学分类技术,建立三层神经元的神经网络,时网络参数进行优化选择以建立最佳网络模型。根据芦丁药品的近红外漫反射光谱,成功地分辨出合格药品和不合格药品。

The possibility of using near infrared reflectance spectroscopy for the quality control of rulin pharmaceuticals was investigated. The artificial neural network chemometrics technique was used to set up a neural network with three layers of neural elements , the parameters were optimized to produce the best network model, and the qualified pharmaceuticals of rutin were successfully identified from the poor based on the near infrared reflectance spectras.